Research map / Vision-language and multimodal / Cross-modal learning
End-to-End Multi-Modal Diffusion Mamba
Chunhao Lu, Qiang Lu, Meichen Dong, Jake Luo
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use 6 scan switch sequences instead of 3 (ablation) | MDM · ImageNet 256x256 (CFG) | FID: 3.96 -> 2.49 | Improved |
| use 6 scan switch sequences instead of 3 (ablation) | MDM · ImageNet 256x256 (CFG) | FPS (log scale): 1.405 -> 1.357 | Hurt |
| use Mamba block instead of Transformer (ablation) | MDM · ImageNet 256x256 (CFG) | FID: 6.72 -> 2.49 | Improved |
| use Mamba block instead of Transformer (ablation) | MDM · ImageNet 256x256 (CFG) | FPS (log scale): 1.914 -> 1.357 | Hurt |
| visual instruction tuning (InstructMDM vs MDM) | MDM · COCO captioning | CIDEr: 109.6 -> 122.1 | Improved |
| visual instruction tuning (InstructMDM vs MDM) | MDM · VQAv2 | accuracy: 60.3 -> 66.7 | Improved |
| visual instruction tuning (InstructMDM vs MDM) | MDM · GSM8K | accuracy: 40.5 -> 46.0 | Improved |
| visual instruction tuning (InstructMDM vs MDM) | MDM · MMLU | accuracy: 54.4 -> 59.2 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 3 on most shared results.
- Show-O — Show-o: One Single Transformer to Unify Multimodal Understanding and Generation (ICLR 2025) · better on 1 of 2 shared results
- JanusFlow — JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation (CVPR 2025) · better on 0 of 1 shared result
- NExT-GPT (7B) — NExT-GPT: Any-to-Any Multimodal LLM (ICML 2024) · better on 0 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Dual Diffusion for Unified Image Generation and Understanding (CVPR 2025 · similarity 0.89)
- Diffusion Models for Multi-Task Generative Modeling (ICLR 2024 · similarity 0.88)
- The Design Space of Tri-Modal Masked Diffusion Models (NeurIPS 2026 · similarity 0.87)
- MMAR: Towards Lossless Multi-Modal Auto-Regressive Probabilistic Modeling (CVPR 2025 · similarity 0.87)
- Towards General Modality Translation with Contrastive and Predictive Latent Diffusion Bridge (NeurIPS 2025 · similarity 0.86)
- MMaDA: Multimodal Large Diffusion Language Models (NeurIPS 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
